6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-18 10:31:57 +00:00
Code Issues Projects Releases Wiki Activity
97be10d98f
llvm-6502/test/CodeGen/R600/fp32_to_fp16.ll

15 lines
627 B
LLVM
Raw Normal View History

R600/SI: Add support for llvm.convert.{to|from}.fp16 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212676 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-10 03:22:20 +00:00
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
CodeGen: extend f16 conversions to permit types > float. This makes the two intrinsics @llvm.convert.from.f16 and @llvm.convert.to.f16 accept types other than simple "float". This is only strictly needed for the truncate operation, since otherwise double rounding occurs and there's no way to represent the strict IEEE conversion. However, for symmetry we allow larger types in the extend too. During legalization, we can expand an "fp16_to_double" operation into two extends for convenience, but abort when the truncate isn't legal. A new libcall is probably needed here. Even after this commit, various target tweaks are needed to actually use the extended intrinsics. I've put these into separate commits for clarity, so there are no actual tests of f64 conversion here. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213248 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-17 10:51:23 +00:00
declare i16 @llvm.convert.to.fp16.f32(float) nounwind readnone
R600/SI: Add support for llvm.convert.{to|from}.fp16 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212676 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-10 03:22:20 +00:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218776 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:15:17 +00:00
; SI-LABEL: {{^}}test_convert_fp32_to_fp16:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221350 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-05 14:50:53 +00:00
; SI: buffer_load_dword [[VAL:v[0-9]+]]
; SI: v_cvt_f16_f32_e32 [[RESULT:v[0-9]+]], [[VAL]]
; SI: buffer_store_short [[RESULT]]
R600: rename misleading fp16 test. This test is actually going in the opposite direction to what the filename and function name suggested. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213358 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-18 08:43:30 +00:00
define void @test_convert_fp32_to_fp16(i16 addrspace(1)* noalias %out, float addrspace(1)* noalias %in) nounwind {
R600/SI: Add support for llvm.convert.{to|from}.fp16 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212676 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-10 03:22:20 +00:00
%val = load float addrspace(1)* %in, align 4
CodeGen: extend f16 conversions to permit types > float. This makes the two intrinsics @llvm.convert.from.f16 and @llvm.convert.to.f16 accept types other than simple "float". This is only strictly needed for the truncate operation, since otherwise double rounding occurs and there's no way to represent the strict IEEE conversion. However, for symmetry we allow larger types in the extend too. During legalization, we can expand an "fp16_to_double" operation into two extends for convenience, but abort when the truncate isn't legal. A new libcall is probably needed here. Even after this commit, various target tweaks are needed to actually use the extended intrinsics. I've put these into separate commits for clarity, so there are no actual tests of f64 conversion here. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213248 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-17 10:51:23 +00:00
%cvt = call i16 @llvm.convert.to.fp16.f32(float %val) nounwind readnone
R600/SI: Add support for llvm.convert.{to|from}.fp16 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212676 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-10 03:22:20 +00:00
store i16 %cvt, i16 addrspace(1)* %out, align 2
ret void
}
Reference in New Issue Copy Permalink